# Open Source Repo Polish

> Audit and improve an open-source repository's README, bilingual presentation, visual hierarchy, onboarding, community health, trust signals, issue and pull-request surfaces, and GitHub metadata. Use when a repository needs polishing, beautification, open-source readiness, README redesign, clearer installation, contributor setup, or a measured repository-health pass.

- **Type:** Skill
- **Install:** `agentstack add skill-offwhite-del-open-source-repo-polish-open-source-repo-polish`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [Offwhite-Del](https://agentstack.voostack.com/s/offwhite-del)
- **Installs:** 0
- **Category:** [Developer Tools](https://agentstack.voostack.com/c/developer-tools)
- **Latest version:** 0.1.0
- **License:** Apache-2.0
- **Upstream author:** [Offwhite-Del](https://github.com/Offwhite-Del)
- **Source:** https://github.com/Offwhite-Del/launch-sieve/tree/main/plugins/repo-polish/skills/open-source-repo-polish

## Install

```sh
agentstack add skill-offwhite-del-open-source-repo-polish-open-source-repo-polish
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# LaunchSieve

Improve repository comprehension and trust before decoration. A polished repository makes its purpose, first verified result, evidence limits, safety boundaries, and contribution path obvious.

## Workflow

1. Read applicable repository instructions, current state, release evidence, and `git status`. Preserve unrelated work.
2. Establish the project purpose, intended users, maturity, canonical installation path, and one representative first-run result.
3. Run the bundled audit read-only:

   ```bash
   node /scripts/audit-repo.mjs --root  --json
   ```

4. Verify remote facts separately when GitHub access is available: description, topics, default branch, latest release, CI, community profile, security reporting, and social preview. Do not infer them from local files.
5. Report findings as `Fact / Inference / Proposal / Blocked`. Rank them by comprehension, onboarding, trust, accessibility, and only then visual distinction.
6. Read [repository-health.md](references/repository-health.md). Read [design-lenses.md](references/design-lenses.md) when visual work is in scope, and [evaluation-rubric.md](references/evaluation-rubric.md) before final validation.
7. Choose one named aesthetic direction grounded in the project's purpose and audience. Explain the memorable element and what will remain deliberately plain.
8. Propose the smallest coherent change set. Keep bilingual documents semantically aligned, but do not translate code, identifiers, or commands.
9. Apply only authorized changes on a branch. Reuse project assets; do not introduce a site, framework, font, animation, or dependency unless the outcome requires it.
10. Render every changed visual asset. Validate local links, document structure, issue-form syntax, package contents, tests, secrets, and the public first-run path.
11. Publish through the repository's normal pull-request workflow. Recheck the public page and remote metadata after merge.

## Design decision order

1. **Truth:** no fabricated claims, badges, benchmarks, compatibility, users, or testimonials.
2. **Purpose:** the first screen states what the project is, for whom, and its real boundary.
3. **Path:** one copyable route reaches a verified result quickly.
4. **Trust:** status, evidence quality, privacy, security, support, and rollback are explicit.
5. **Hierarchy:** layout, type, color, and imagery guide scanning.
6. **Distinction:** one project-specific visual idea makes the repository memorable.

## Boundaries

- Default to audit and proposal when the user did not authorize edits or publishing.
- Never read or publish `.env`, credentials, private transcripts, private plans, backups, receipts, or secret values.
- Never add fake badges, inflated statistics, inactive community links, or unsupported platform claims.
- Do not copy Anthropic, OpenAI, Apple, or another project's protected logos, fonts, layouts, or brand assets. Use public guidance as a reasoning lens only.
- Do not turn static GitHub documentation into a motion showcase. Motion principles apply only to an actual interactive surface.
- Do not equate GitHub Community Profile percentage or the bundled heuristic score with overall project quality.
- Stop when the page is clear, trustworthy, visually coherent, accessible, and verified. More content is not automatically more polish.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [Offwhite-Del](https://github.com/Offwhite-Del)
- **Source:** [Offwhite-Del/launch-sieve](https://github.com/Offwhite-Del/launch-sieve)
- **License:** Apache-2.0

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** yes
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-offwhite-del-open-source-repo-polish-open-source-repo-polish
- Seller: https://agentstack.voostack.com/s/offwhite-del
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.